mlsanityData to 14 Oct 2026

Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification

arXiv 2411.17571 ↗First posted 26 Nov 2024eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

White Matter Hyperintensities (WMH) are key neuroradiological markers of small vessel disease present in brain MRI. Assessment of WMH is important in research and clinics. However, WMH are challenging to segment due to their high variability in shape, location, size, poorly defined borders, and similar intensity profile to other pathologies (e.g stroke lesions) and artefacts (e.g head motion). In this work, we assess the utility and semantic properties of the most effective techniques for uncertainty quantification (UQ) in segmentation for the WMH segmentation task across multiple test-time data distributions. We find UQ techniques reduce 'silent failure' by identifying in UQ maps small WMH clusters in the deep white matter that are unsegmented by the model. A combination of Stochastic Segmentation Networks with Deep Ensembles also yields the highest Dice and lowest Absolute Volume Difference % (AVD) score and can highlight areas where there is ambiguity between WMH and stroke lesions. We further demonstrate the downstream utility of UQ, proposing a novel method for classification of the clinical Fazekas score using spatial features extracted from voxelwise WMH probability and UQ maps. We show that incorporating WMH uncertainty information improves Fazekas classification performance and calibration. Our model with (UQ and spatial WMH features)/(spatial WMH features)/(WMH volume only) achieves a balanced accuracy score of 0.74/0.67/0.62, and root brier score of 0.65/0.72/0.74 in the Deep WMH and balanced accuracy of 0.74/0.73/0.71 and root brier score of 0.64/0.66/0.68 in the Periventricular region. We further demonstrate that stochastic UQ techniques with high sample diversity can improve the detection of poor quality segmentations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 111 references that are in the map. First posted on arXiv 26 Nov 2024.

Builds on

52 of 111 references.

References · 52

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  5. 2016Variational Inference: A Review for Statisticianscited by 1,472
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  8. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  9. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  10. 2019Deep Evidential Regressioncited by 355
  11. 2021Ensemble deep learning: A reviewcited by 284
  12. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 283
38 more
  1. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
  2. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
  3. 2021Trustworthy AI: From Principles to Practicescited by 207
  4. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  5. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 168
  6. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  7. 2015Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networkscited by 139
  8. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
  9. 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
  10. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 101
  11. 2018Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentationcited by 76
  12. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  13. 2024Variational Bayesian Last Layerscited by 69
  14. 2019A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguitiescited by 65
  15. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  16. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 63
  17. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  18. 2020Neural Ensemble Search for Uncertainty Estimation and Dataset Shiftcited by 56
  19. 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
  20. 2019Supervised Uncertainty Quantification for Segmentation with Multiple Annotationscited by 42
  21. 2021Is segmentation uncertainty useful?cited by 37
  22. 2022TBraTS: Trusted Brain Tumor Segmentationcited by 30
  23. 2022Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learningcited by 27
  24. 2018Evaluating the Impact of Intensity Normalization on MR Image Synthesiscited by 26
  25. 2021Deep Deterministic Uncertainty for Semantic Segmentationcited by 24
  26. 2021On Stein Variational Neural Network Ensemblescited by 21
  27. 2022Region-Based Evidential Deep Learning to Quantify Uncertainty and Improve Robustness of Brain Tumor Segmentationcited by 21
  28. 2020Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Priorcited by 18
  29. 2021Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentationcited by 17
  30. 2023Robust T-Loss for Medical Image Segmentationcited by 14
  31. 2021Improving Aleatoric Uncertainty Quantification in Multi-Annotated Medical Image Segmentation with Normalizing Flowscited by 13
  32. 2023Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Expertscited by 12
  33. 2022Generalized Probabilistic U-Net for medical image segementationcited by 10
  34. 2021Robust White Matter Hyperintensity Segmentation on Unseen Domaincited by 8
  35. 2022Improving robustness and calibration in ensembles with diversity regularizationcited by 8
  36. 2022Brain tumour segmentation with incomplete imaging datacited by 7
  37. 2023Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentationcited by 7
  38. 2023Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantificationcited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.